[object Object][object Object][object Object]undefined[object Object]

• Description: Computes the backpropagation of [object Object].

• Formula:

  (1) When [object Object] is not set to [object Object]:

  $$permutedTokensGrad[outIndex[i]] = unpermutedTokensGrad[permuteTokenId[i]]$$ $$permutedProbsGrad = permutedTokensGrad * permutedTokensOptional$$ $$probsGradExpertOrder = \sum_{j=0}^{hidden\_size}(permutedProbsGrad_{i,j})$$
  • When [object Object] is set to [object Object]:
  $$probsGradOut = masked\_scatter(routingMapOptional^T,probsGradExpertOrder)$$ $$permutedProbs = probsOptional^T.masked\_select(routingMapOptional^T)$$ $$permutedTokensGradOut = permutedProbs.unsqueeze(-1) * permutedTokensGrad$$
  • When [object Object] is set to [object Object]:
  $$probsGradOut[permuteTokenId[i], outIndex[i]/capacity] = probsGradExpertOrder[outIndex[i]]$$ $$permutedProbs[outIndex[i]] = probsOptional.view(1)[i]$$ $$permutedTokensGradOut = permutedProbs * permutedTokensGrad$$

  (2) When [object Object] is set to [object Object]:

  $$permutedTokensGradOut[outIndex[i]] = unpermutedTokensGrad[permuteTokenId[i]]$$
  1. [object Object] indicates the size of the first dimension of [object Object].
  2. When [object Object] is set to [object Object], each expert can process a fixed number of tokens, which is specified by [object Object]. The first dimension of the input [object Object] is the value specified by [object Object], which indicates the number of experts. The 0th dimension of the input [object Object] is [object Object] * [object Object]. The value of [object Object] can be computed based on the two dimensions.
  3. When [object Object] is set to [object Object], each token is processed by a fixed number of experts, which is specified by [object Object]. The 0th dimension of the input [object Object] is specified by [object Object], which indicates the number of tokens. The 0th dimension of the input [object Object] is the value specified by [object Object] * [object Object]. The value of [object Object] can be computed based on the two dimensions.

[object Object]

Each operator has calls. First, [object Object] is called to obtain the workspace size required for computation and the executor covering the operator computation process. Then, [object Object] is called to perform computation.

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter verification. The following errors may be thrown.

  [object Object]

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object] status code. For details, see .

[object Object]

• Deterministic computation:

  • [object Object] defaults to deterministic implementation.

• When the input [object Object] is not left empty and [object Object] is set to [object Object], the value of [object Object] is less than or equal to that of [object Object], and the value is less than or equal to [object Object].

• When the input [object Object] is not left empty and [object Object] is set to [object Object], the value of [object Object] is less than or equal to that of [object Object].

[object Object]

The following example is for reference only. For details, see .